Referring Video Object Segmentation on A2D Sentences v1.0 (test)
81.2IoU OverallLoSh-S
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| LoSh-SBackbone=Video-Swin-B, Number of input frames (w)=52023.06 | 81.2 | — | — | — | — | — | 59.9 | 73.1 | |
| SgMgBackbone=Video-Swin-B, Number of input frames (w)=52023.06 | 79.9 | — | — | — | — | — | 58.5 | 72 | |
| LoSh-SBackbone=Video-Swin-T, Number of input frames (w)=52023.06 | 79.3 | — | — | — | — | — | 57.6 | 71.6 | |
| ReferFormerBackbone=Video-Swin-B2023.06 | 78.6 | — | — | — | — | — | 55 | 70.3 | |
| SgMgBackbone=Video-Swin-T, Number of input frames (w)=52023.06 | 78 | — | — | — | — | — | 56.1 | 70.4 | |
| LoSh-MBackbone=Video-Swin-T, Number of input frames (w)=82023.06 | 72.9 | — | — | — | — | — | 47.8 | 64.9 | |
| LoSh-M w/ MShBackbone=Video-Swin-T2023.06 | 72.9 | — | — | — | — | — | 47.8 | 64.8 | |
| LoSh-M w/ Bi-CABackbone=Video-Swin-T2023.06 | 72.8 | — | — | — | — | — | 47.6 | 64.7 | |
| MANetVenue=-2022.07 | 72.6 | 73.4 | 68.2 | 57.9 | 38.9 | 13.2 | 47.1 | 63.2 | |
| LoSh-M w/o CABackbone=Video-Swin-T2023.06 | 72.5 | — | — | — | — | — | 47.3 | 64.5 | |
| LoSh-M w/ Inv-CABackbone=Video-Swin-T2023.06 | 72.5 | — | — | — | — | — | 47.2 | 64.3 | |
| LoSh-M w/o LlsiBackbone=Video-Swin-T2023.06 | 72.3 | — | — | — | — | — | 46.1 | 63.8 | |
| LoSh-M w/o ShBackbone=Video-Swin-T2023.06 | 71.1 | — | — | — | — | — | 45.4 | 62.6 | |
| MTTRVenue=CVPR222022.07 | 70.2 | 72.1 | 68.4 | 60.7 | 45.6 | 16.4 | 44.7 | 61.8 | |
| MTTRBackbone=Video-Swin-T, Number of input frames (w)=82023.06 | 70.2 | — | — | — | — | — | 44.7 | 61.8 | |
| CSTMVenue=CVPR212022.07 | 66.2 | 65.4 | 58.9 | 49.7 | 33.3 | 9.1 | 39.9 | 56.1 | |
| PolarRPEVenue=IJCAI202022.07 | 66.1 | 63.4 | 57.9 | 48.3 | 32.2 | 8.3 | 38.8 | 52.9 | |
| CMPC-VVenue=T-PAMI212022.07 | 65.3 | 65.5 | 59.2 | 50.6 | 34.2 | 9.8 | 40.4 | 57.3 | |
| CMPC-VBackbone=I3D2023.06 | 65.3 | — | — | — | — | — | 40.4 | 57.3 | |
| CCMAVenue=ACMMM212022.07 | 63.2 | 65.3 | 64.5 | 61.1 | 49.1 | 17.4 | 48 | 55.5 | |
| CMDyVenue=AAAI202022.07 | 62.3 | 60.7 | 52.5 | 40.5 | 23.5 | 4.5 | 33.3 | 53.1 | |
| CMSA+CFSAVenue=T-PAMI212022.07 | 61.8 | 48.7 | 43.1 | 35.8 | 23.1 | 5.2 | — | 43.2 | |
| ACGAVenue=ICCV192022.07 | 60.1 | 55.7 | 45.9 | 31.9 | 16 | 2 | 27.4 | 49 | |
| VT-CapsuleVenue=CVPR202022.07 | 56.8 | 52.6 | 45 | 34.5 | 20.7 | 3.6 | 30.3 | 46 | |
| A2DSVenue=CVPR182022.07 | 55.1 | 50 | 37.6 | 23.1 | 9.4 | 0.4 | 21.5 | 42.6 | |
| Gavrilyuk et al.Backbone=I3D2023.06 | 53.6 | — | — | — | — | — | 19.8 | 42.1 |